123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081 |
- import datetime
- import logging
- import time
- from typing import List, Optional
- import click
- from celery import shared_task
- from langchain.schema import Document
- from werkzeug.exceptions import NotFound
- from core.index.index import IndexBuilder
- from extensions.ext_database import db
- from extensions.ext_redis import redis_client
- from models.dataset import DocumentSegment
- @shared_task(queue='dataset')
- def update_segment_keyword_index_task(segment_id: str):
- """
- Async update segment index
- :param segment_id:
- Usage: update_segment_keyword_index_task.delay(segment_id)
- """
- logging.info(click.style('Start update segment keyword index: {}'.format(segment_id), fg='green'))
- start_at = time.perf_counter()
- segment = db.session.query(DocumentSegment).filter(DocumentSegment.id == segment_id).first()
- if not segment:
- raise NotFound('Segment not found')
- indexing_cache_key = 'segment_{}_indexing'.format(segment.id)
- try:
- dataset = segment.dataset
- if not dataset:
- logging.info(click.style('Segment {} has no dataset, pass.'.format(segment.id), fg='cyan'))
- return
- dataset_document = segment.document
- if not dataset_document:
- logging.info(click.style('Segment {} has no document, pass.'.format(segment.id), fg='cyan'))
- return
- if not dataset_document.enabled or dataset_document.archived or dataset_document.indexing_status != 'completed':
- logging.info(click.style('Segment {} document status is invalid, pass.'.format(segment.id), fg='cyan'))
- return
- kw_index = IndexBuilder.get_index(dataset, 'economy')
- # delete from keyword index
- kw_index.delete_by_ids([segment.index_node_id])
- # add new index
- document = Document(
- page_content=segment.content,
- metadata={
- "doc_id": segment.index_node_id,
- "doc_hash": segment.index_node_hash,
- "document_id": segment.document_id,
- "dataset_id": segment.dataset_id,
- }
- )
- # save keyword index
- index = IndexBuilder.get_index(dataset, 'economy')
- if index:
- index.update_segment_keywords_index(segment.index_node_id, segment.keywords)
- end_at = time.perf_counter()
- logging.info(click.style('Segment update index: {} latency: {}'.format(segment.id, end_at - start_at), fg='green'))
- except Exception as e:
- logging.exception("update segment index failed")
- segment.enabled = False
- segment.disabled_at = datetime.datetime.utcnow()
- segment.status = 'error'
- segment.error = str(e)
- db.session.commit()
- finally:
- redis_client.delete(indexing_cache_key)
|